Prompts
Prompt engineering and templates
huashu-slides
by alchaincyf
从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
Lobster
by openclaw
One-off tasks that won't be repeated
求职类文章写作 Skill
by itwanger
```
oracle
by openclaw
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
fine-tuning-with-trl
by Orchestra-Research
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
gguf-quantization
by Orchestra-Research
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
sglang
by Orchestra-Research
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
clone
by ykdojo
Clone the current conversation so the user can branch off and try a different approach.
developing-with-ai-sdk
by laravel
Builds AI agents, generates text and chat responses, produces images, synthesizes audio, transcribes speech, generates vector embeddings, reranks documents, and manages files and vector stores using the Laravel AI SDK (laravel/ai). Supports structured output, streaming, tools, conversation memory, middleware, queueing, broadcasting, and provider failover. Use when building, editing, updating, debugging, or testing any AI functionality, including agents, LLMs, chatbots, text generation, image generation, audio, transcription, embeddings, RAG, similarity search, vector stores, prompting, structured output, or any AI provider (OpenAI, Anthropic, Gemini, Cohere, Groq, xAI, ElevenLabs, Jina, OpenRouter).
pend
by bfly123
View latest reply from AI provider (gemini/codex/opencode/droid/claude).
doc-coauthoring
by ThinkInAIXYZ
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
skill-creator
by ThinkInAIXYZ
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
ping
by bfly123
Test connectivity with AI provider (gemini/codex/opencode/droid/claude).
rwkv-architecture
by Orchestra-Research
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
pend
by bfly123
View latest reply from AI provider (gemini/codex/opencode/droid/claude).
pend
by bfly123
View latest reply from AI provider (gemini/codex/opencode/droid/claude).
ping
by bfly123
Test connectivity with AI provider (gemini/codex/opencode/droid/claude).
deep-research
by feiskyer
'深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（claude -p）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场景。'
aigcpanel-skills
by modstart-lib
通过 AigcPanel Pro 内置 HTTP 接口调用本地 AI 模型。当需要列出可用模型、调用模型生成内容、或查询任务结果时使用本技能。适用场景：自动化脚本调用 AI 模型、外部程序集成 AigcPanel Pro、批量处理任务。
omx-setup
by Yeachan-Heo
Setup and configure oh-my-codex using current CLI behavior
ctf-ai-ml
by ljagiello
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.
copilot-sdk
by github
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.
skill-creator
by iOfficeAI
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
prompt-optimize
by labring
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.